检索结果-内蒙古大学图书馆

Rethinking Masked Autoencoder for Salient Object Detection in Optical Remote Sensing Images From a Pseudo Image Pretraining Perspective

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Fu, Yuxiang Fang, Wei Sheng, Victor S. Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Soochow University Provincial Key Laboratory for Computer Information Processing Technology Suzhou215031 China Texas Tech University Department of Computer Science LubbockTX79409 United States

Recently masked autoencoder (MAE) has achieved great success in visual representation learning and delivered promising potential in many downstream vision tasks. However, due to the lack of a saliency supervision signal in the original MAE, almost no saliency information can be learned from the masked image reconstruction process. Therefore, salient object detection (SOD) can hardly benefit from MAE pretraining. To address this issue, we integrate the SOD model and saliency supervision in MAE and propose a simple and effective framework for dynamic hybrid masking MAE (DHMMAE), utilizing MAE with dynamic hybrid masking (DHM) ratios to pretrain SOD model. Specifically, we treat MAE as an online data augmenter to generate endless pseudo images for the SOD model to predict saliency maps, where saliency supervision is employed to ensure that the model can learn robust saliency prior knowledge from the reconstructed images. Besides, we propose a simple and novel network EANet driven by DHMMAE pretraining for SOD in optical remote sensing images (ORSIs). Two key modules are designed for EANet to further enhance its performance: the enhanced diverse feature aggregation module (EDFAM) and the adjacent-context shuffle spatial attention module (ASSAM). EDFAM aggregates diverse features via three different types of convolution layers and enhances them by convolution block attention module (CBAM). ASSAM captures spatial location information of salient objects by employing channel shuffle operation and weighted spatial attention mechanism on the fused adjacent context. Experiments on three ORSI-SOD datasets demonstrate that our proposed method outperforms the cutting-edge methods. © 1980-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

SMGC-SBERT: A Multi-Feature Fusion Chinese Short Text Similarity Computation Model Based on Optimised SBERT

SMGC-SBERT: A Multi-Feature Fusion Chinese Short Text Simila...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Shuo Zhao Qiliang Gu Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Chinese short text similarity computation stands as a pivotal task within natural language processing, garnering significant attention. However, existing models grapple with limitations in handling intricate semantic relationships, such as the challenge of discerning subtle semantic nuances in text, inadequacies in effectively integrating diverse levels of semantic information, and the struggle to capture polysemous meanings accurately. In addressing these issues, this paper introduces an innovative Chinese short text similarity computation model, SMGC-SBERT. This model addresses shortcomings of the existing models by employing a multi-module fusion strategy, thereby enabling a more precise measurement of semantic similarity between texts. Primarily, the model incorporates SAT embedding to acquire phrase-level semantic information and leverages the MS-BERT model to encode text, improving the model's comprehension of textual polysemy and obtaining richer semantic representation. Then, the fusion of module features, including multi-branch convolutional networks and mix pooling, enables the extraction of textual features from varied levels, bolstering the model's representational capacity. Additionally, to further reduce overfitting risks while improving accuracy and other performance, a multi-layer feature adjustment network is utilized for short text similarity calculation. The final resultant experimental findings showcase the superiority of the SMGC-SBERT model over other neural network models, demonstrating significant advancements across both Chinese-SNLI and CCKS2018_Task3 Chinese short text datasets.

关键词： Deep learning Computational modeling Semantics Neural networks Feature extraction Natural language processing Multilingual Convolutional neural networks Cybernetics Overfitting

来源：评论

学校读者我要写书评

暂无评论

A Novel Text Matching Model Based on Multilayer Coding and Feature Enhancement

A Novel Text Matching Model Based on Multilayer Coding and F...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yu Zhang Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

With the rapid development of Natural Language processing (NLP), text matching has become the basis of many downstream tasks in NLP, and the study of text matching is of great research significance for solving tasks such as question and answer and information retrieval in NLP. Most of the current text matching methods tend to have problems such as mismatch of grammatical structures and insufficient interaction information in sentences. In order to solve the problems of insufficient interaction information and lack of features and ability to capture keyword and sequence information in text matching, this paper proposes a text matching method based on multi-layer coding and soft attention mechanism. The method first embeds the text and sends it to a gating module for processing, then sends the processed result to a module containing a combination of multilayer coding and soft attention mechanism for further operations such as multiple alignment, and finally sends it to a classifier containing a three-layer fully-connected network for predicting whether the input text pairs match or not. The two modules proposed in this paper are practically feasible, and comparison and ablation experiments have been conducted on the publicly available datasets LCQMC dataset and BQ dataset, and the experimental results show that the two modules improve the accuracy of text matching by 2.44% and 1.02%, respectively.

关键词： Attention mechanisms Accuracy Computational modeling Impedance matching Nonhomogeneous media information retrieval Encoding

来源：评论

学校读者我要写书评

暂无评论

MRLATO: An Adaptive Task Offloading Mechanism Based on Meta Reinforcement Learning in Edge Computing Environment

引用

IEEE Transactions on Vehicular technology 2025年

作者： Zhang, Peiying Liu, Jiamin Guizani, Maher Wang, Jian Kumar, Neeraj Tan, Lizhuang Qingdao Institute of Software College of Computer Science and Technology Qingdao266580 China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao266580 China Ministry of Education Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China University of Texas Arlington Computer Science and Engineering Department TX United States College of Science Qingdao266580 China Thapar University Department of Computer Science and Engineering Patiala147004 India Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China

Traditional cloud computing models struggle to meet the requirements of latency-sensitive applications when processing large amounts of data. As a solution, Multi-access Edge Computing (MEC) extends computing resources to the edge of the network to reduce processing delays and improve user experience. However, in dynamically changing edge computing environments, effective decision making on whether to offload tasks to edge servers remains a core challenge. For this purpose, we propose MRLATO, an adaptive task offloading mechanism based on Meta Reinforcement Learning (MRL), which exploits a large amount of a priori knowledge of different tasks to achieve fast adaptation. The task offloading process is modelled as multiple Markov Decision Processes (MDPs) and solved using a Sequence to Sequence (Seq2Seq) neural network integrating multi-head attention and recursive task sequencing. It is shown by the experimental results that the proposed method has the lowest latency in all experimental settings and the convergence efficiency is improved by 14.06% compared to the traditional Deep Reinforcement Learning (DRL) algorithm. This research fully demonstrates the significant benefits of the deep integration of MRL with the edge computing domain, providing new optimisation ideas for task offloading decisions. © 1967-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Double-Graph Representation With Relational Enhancement for Emotion-Cause Pair Extraction

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年第6期36卷 10859-10873页

作者： Ming Zhang Zhe Chen Vasile Palade Tao Lu Liya Wang Junchi Zhang Yanduo Zhang Hubei Provincial Key Laboratory of Intelligent Robot the School of Computer Science and Engineering and the School of Artificial Intelligence Wuhan Institute of Technology Wuhan China Institute of Information Technology Anhui Vocational College of Defense Technology Lu’An Anhui China Centre for Computational Science and Mathematical Modelling Coventry University Coventry U.K. Zhejiang Industry and Trade Vocational College Wenzhou China School of Artificial Intelligence Jianghan University Wuhan China Computer School Hubei University of Arts and Science Xiangyang China

The emotion-cause pair extraction (ECPE) task is to simultaneously extract emotions and causes as pairs (EC-pairs) from documents, which is important for natural language processing. Previous research tackled this task via a two-step approach, which first predicts separately the emotion and cause clauses, and then pairs them up by using a binary classifier. However, such a two-step approach may suffer from the possible propagation of errors, and it neglects the interaction between emotions and causes. In this article, an end-to-end double-graph method with relational enhancement (DGRE) is proposed to stimulate two relationship modes among clauses, i.e., semantic dependence and logical dependence. First, two united graph encoders are established to embed the semantic dependence into the representation of clauses and pairs. The first encoder is built on graph attention networks (GATs) for clause-level representation, the result of which is used by a relational graph convolutional network (RGCN) for the refinement of pair-level representation. Aiming to enhance the fitting ability of logical dependence, the emotion-type classification task is introduced into the multitask learning framework of GATs, which can effectively distinguish the logical relations between clauses according to their emotion types. Moreover, seven types of dependence relations have been designed for the node connections in RGCN, which emphasize the contextual interaction and clustering among neighboring nodes. Experiments on a benchmark Chinese corpus demonstrate that the proposed DGRE approach could effectively establish the communication mechanism between clauses and pairs from multiple perspectives, and comparisons with state-of-the-art (SOTA) models well validate its effectiveness.

关键词： Semantics Electronic mail Cause effect analysis Predictive models Context modeling Correlation Stacking Mutual information Learning systems Iterative methods

来源：评论

学校读者我要写书评

暂无评论

FERI: Feature Enhancement and Relational Interaction for Image-text Matching

FERI: Feature Enhancement and Relational Interaction for Ima...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yu Zhang Jianqiang Zhang Gongpeng Song Qin Lu Shuo Zhao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignment between the two modalities. However, the existing methods have the problem that the meaning expressed in the image or the complex narrative in the text cannot be fully understood due to insufficient feature extraction. Moreover, due to the essential modal differences between images and texts, how to effectively and accurately align the semantic contents in images and texts has become the key of research. In order to solve the above problems, this paper proposes a method based on feature enhancement and relationship interaction. When processing images, the proposed method fuses labeled features, region features and location features to represent images. When processing text, a combination of Bi-GRU and self-attention mechanism is used to represent the text. In order to further align the semantic content in images and texts accurately, this paper improves two relational interaction mechanisms by identifying connection relationships and learning association relationships. Thus, the relation enhanced embedding is obtained. Finally, it calculated the similarity of the enhanced embedding to judge the matching degree of the image and text. Extensive experiments on the public datasets Flickr30K and MSCOCO demonstrate the effectiveness of our method.

关键词： computer vision Fuses Image matching Semantics Feature extraction Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection

arXiv

引用

arXiv 2024年

作者： Liang, Hanzhe Xie, Guoyang Hou, Chengbin Wang, Bingshu Gao, Can Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Audencia Financial Technology Institute Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Intelligent Manufacturing CATL Ningde China School of Computing and Artificial Intelligence Fuyao University of Science and Technology Fuzhou China School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we introduce a straightforward method named Internal Spatial Modality Perception (ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine (SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction module for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further aligning precise spatial structure. Extensive experiments validate the effectiveness of our proposed method, achieving object-level and pixel-level AUROC improvements of 4.2% and 13.1%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and is verified in both classification and segmentation tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similarity Computation Model with Attention Mechanism

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similar...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Shuo Zhao Yiyun Xing Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Text semantic similarity is a crucial research area in Natural Language processing (NLP). However, traditional methods for calculating the similarity of short Chinese texts often fall short in accuracy and other crucial aspects. The Bidirectional Long Short-Term Memory Network (BiLSTM) has demonstrated remarkable performance in computing the similarity of short Chinese texts by effectively capturing long-range dependencies and semantic information. Additionally, the multi-head attention mechanism considers the interaction between different text locations and semantic information, enhancing the model’s representative capacity. Building upon this foundation, our paper proposes an enhanced model known as SCTbilstmAttRdrop (SCTAR). This model is constructed based on a multilayer BiLSTM architecture and incorporates an SE-gated convolutional module and a convolutional multi-head attention-aware model. We conducted extensive evaluations using two Chinese short text datasets, Chinese-SNLI and CCKS2018_Task3. The experimental results unequivocally demonstrate that our SCTAR model surpasses other common methods in terms of accuracy, precision, recall, and F1 scores when tasked with computing the similarity of Chinese short texts.

关键词： Accuracy Attention mechanisms Computational modeling Semantics Bidirectional control Feature extraction Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

DQPS: An Intelligent Multi-Hop Computation Offloading Scheme for Workflow Applications in Vehicular Edge Computing Networks

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Lin, Bing Chen, Qiaoxin Chen, Xing Jia, Wen-Kang Lu, Yu Xiong, Neal N. Fujian Normal University College of Physics and Energy Fujian Provincial Key Laboratory of Quantum Manipulation and New Energy Materials Fuzhou350117 China Fujian Provincial Collaborative Innovation Center for Advanced High-Field Superconducting Materials and Engineering Fuzhou350117 China Peking University School of Computer Science 100871 China Xiamen University Department of Informatics and Communication Engineering Xiamen361005 China Fuzhou University College of Computer and Data Science Fuzhou350118 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350118 China Fujian Normal University College of Photonic and Electronic Engineering Fuzhou350117 China Fujian Normal University Concord University College Fuzhou350117 China Sul Ross State University Department of Computer Mathematical and Physical Sciences AlpineTX79830 United States

Vehicular Edge Computing (VEC) is a feasible solution for autonomous driving as it can offload latency-sensitive and computation-intensive tasks from vehicle terminals to roadside units (RSUs) for real-time processing. Due to the high computational resource the workflow applications (i.e., autonomous driving) required, the small vehicle-to-RSUs communication range, and the scarce available resources for each vehicle, it might be difficult to accomplish complex workflow applications through the single-hop offloading paradigm in the Internet of Vehicles (IoV). In this paper, we propose a reinforcement learning (RL) based multi-hop computation offloading scheme for workflow applications to reduce their execution latency in the VEC networks, which considers the data dependency in workflow applications as well as the trust relationship and communication interference among RSUs. Firstly, a preprocessing method is employed to merge the cut-edges in a workflow to reduce the offloading scale of tasks and compress the encoding dimension of offloading solutions. Then, a Deep Q-network algorithm using Phase-optimal State update (DQPS) is proposed to update the offloading policy distribution, in which the deviation of the phase-optimal state from the current state is estimated as the reward of RL to promote the algorithm's convergence to adapt the dynamic VEC networks. Simulation results show that DQPS has the best performance compared to other benchmark schemes. Moreover, the latency of the identical applications can be reduced by 2.5%-25.3% through our offloading scheme with a multi-hop model compared to that with the single-hop paradigm in IoV. © 1975-2011 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Decomposed Neural Architecture Search for image denoising

引用

Applied Soft Computing 2022年 124卷

作者： Li, Di Bai, Yunpeng Bai, Zongwen Li, Ying Shang, Changjing Shen, Qiang School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xi'an710129 China Department of Computer Science Faculty of Business and Physical Sciences Aberystwyth University AberystwythSY233DB United Kingdom Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data School of Physics and Electronic Information Yan'an University Yan'an716000 China

In practical applications of deep learning, as the demand for the modeling capability increases, the network size may need to be massively enlarged in response. This may form a significant challenge in practice, especially when facing the dilemma of limited computational resources, making model compression indispensable. It can be time-consuming and interminable to obtain an appropriate network architecture through manual compression. In this paper, we propose an automated method for searching decomposed network architectures, named DNAS (standing for Decomposed Neural Architecture Search). It integrates both tasks of neural architecture search and tensor decomposition based model compression within a unified framework. The method is able to efficiently find a compact network with high performance for image denoising, with respect to memory and runtime. Particularly, using one single V100 GPU, it only takes about 1.5 h to obtain a denoising network on the BSD500 dataset. Experimental results demonstrate that compared with models developed using existing methods, DNAS consumes significantly less inference time and employs much fewer trainable parameters, outperforming existing approaches on both synthetic and real-world denoising datasets. © 2022 Elsevier B.V.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：